Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only, open-world, idempotent, and non-destructive behavior, so the description doesn't need to repeat those. It adds valuable context about series breaks, noting that definitions can change across windows and explaining how to pin a specific window (seriesbreak) with guidance to consult list_series output for window IDs. This is beyond the annotations and helps agents understand the data volatility.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences: the first states the tool's purpose, the second explains the two modes and keyid_filter, and the third addresses the series break nuance. Information is front-loaded, no redundant phrasing, and every sentence earns its place. It's appropriately concise for a moderately complex tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the main functionality (two modes, filtering, series break handling) and gives a high-level sense of what each mode returns. With no output schema, the description doesn't detail the exact response structure, but it explains the data source and the series break mechanism well. The tool is read-only and has optional parameters, so the description is sufficient for an agent to call it correctly, though it could be slightly more explicit about output format.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema descriptions cover all four parameters (100% coverage), so baseline is 3. The description supplements the schema with concrete examples (keyid_filter: 'treasury', 'mbs', 'agency'; seriesbreak: 'SBN2024') and explains the purpose of each mode. This adds practical usage context that the bare schema descriptions lack, raising the score to 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool provides FR 2004 weekly primary dealer survey data, aggregated across all dealers, with two specific modes (list_series and latest). It is specific about the data source and scope, distinguishing it from generic tools. However, it does not explicitly differentiate from sibling nyfed tools (e.g., nyfed_reference_rates), so it loses a point for not naming an alternative.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear instructions on how to use the two modes (list_series to browse catalog, latest for recent values) and explains the keyid_filter and seriesbreak parameters. However, it does not mention when to use this tool versus other NY Fed tools (such as nyfed_repo_operations or nyfed_soma_holdings), so it lacks explicit exclusions or alternatives. The usage guidance is internal to the tool but not comparative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.